Method and apparatus for video recommendation, and refrigerator with screen

Abstract

The present disclosure relates to the technical field of big data analysis, and discloses a method for video recommendation. The method includes: determining a first reference video according to a watching history of a user; determining a collection of recommended videos according to the first reference video; selecting a second reference video from the collection of recommended videos, where videos not selected in the collection of recommended videos are used as candidate videos; and determining recommended videos according to the similarity between the candidate videos and the second reference video. According to the method, a collection of recommended videos is determined according to a watching history of a user, reference videos are selected from the collection of recommended videos, and then recommended videos are determined according to the reference videos, so that the recommended videos are more customized and targeting, matching user requirements and enabling a better user experience.

1 . A method for video recommendation, comprising:
 determining a first reference video according to a watching history of a user;   determining a collection of recommended videos according to the first reference video;   selecting a second reference video from the collection of recommended videos, where videos not selected in the collection of recommended videos are used as candidate videos; and   determining recommended videos according to the similarity between the candidate videos and the second reference video.   
     
     
         2 . The method according to  claim 1 , wherein the step of determining a collection of recommended videos according to the first reference video comprises:
 determining a type of recommended videos according to the first reference video;   determining the collection of recommended videos according to the type of recommended videos.   
     
     
         3 . The method according to  claim 1 , wherein the watching history comprises:
 a history of a latest video a user watched; or   a history of a latest video the user watched for a duration reaching a set threshold value; or   a history of a video the user watched most frequently.   
     
     
         4 . The method according to  claim 2 , wherein the step of determining a type of recommended videos according to the first reference video comprises:
 determining a most frequent type of videos in a set timeframe since the first reference video appears as the type of recommended videos.   
     
     
         5 . The method according to  claim 2 , wherein the step of determining a collection of recommended videos according to the type of recommended videos comprises:
 adding videos corresponding to the type of recommended videos to the collection of recommended videos.   
     
     
         6 . The method according to  claim 1 , wherein the step of selecting a second reference video from the collection of recommended videos comprises:
 selecting a video the user watched for the longest time from the collection of recommended videos as the second reference video, where videos not selected from the collection of recommended videos are used candidate videos; or   randomly selecting one video from the collection of recommended videos as the second reference video, where videos not selected from the collection of recommended videos are used candidate videos.   
     
     
         7 . The method according to  claim 1 , wherein the step of determining recommended videos according to the similarity between the candidate videos and the second reference video comprises:
 acquiring a similarity between each candidate video between the second reference video;   selecting a candidate video with a maximum similarity to the second reference video as a recommended video; or   selecting a candidate video with a minimum similarity to the second reference video as a recommended video; or   selecting a candidate video with a similarity in a set range to the second reference video as a recommended video.   
     
     
         8 . The method according to  claim 7 , wherein the step of acquiring a similarity between each candidate video between the second reference video comprises:
 extracting a first collection of keywords from an introduction text of each candidate video, and extracting a second collection of keywords from the introduction text of the second reference video; and   obtaining the similarity between each candidate video and the second reference video according to the first collection of keywords and the second collection of keywords.   
     
     
         9 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 1  when executing the program instructions. 
     
     
         10 . A refrigerator with a screen, comprising the apparatus for video recommendation according to  claim 9 . 
     
     
         11 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 2  when executing the program instructions. 
     
     
         12 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 3  when executing the program instructions. 
     
     
         13 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 4  when executing the program instructions. 
     
     
         14 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 5  when executing the program instructions. 
     
     
         15 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 6  when executing the program instructions. 
     
     
         16 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 7  when executing the program instructions. 
     
     
         17 . An apparatus for video recommendation comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method for video recommendation according to  claim 8  when executing the program instructions.